{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2V7OTQMRKLCBQJRXSIIMQGLXFR","short_pith_number":"pith:2V7OTQMR","canonical_record":{"source":{"id":"2605.14764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T12:26:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6369523667ba40a7ed9a90d1ff5526383b2425ac672e3e5cf69697e7595d67c1","abstract_canon_sha256":"2f0748ca70e2e568eb32c8fee443760b6968f6a69b4f081584bc1f83c399921e"},"schema_version":"1.0"},"canonical_sha256":"d57ee9c19152c41826379210c819772c641f3193627b5cc65b13d8d14d3a6c61","source":{"kind":"arxiv","id":"2605.14764","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14764","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14764v1","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14764","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"2V7OTQMRKLCB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2V7OTQMRKLCBQJRX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2V7OTQMR","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2V7OTQMRKLCBQJRXSIIMQGLXFR","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14764","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T12:26:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6369523667ba40a7ed9a90d1ff5526383b2425ac672e3e5cf69697e7595d67c1","abstract_canon_sha256":"2f0748ca70e2e568eb32c8fee443760b6968f6a69b4f081584bc1f83c399921e"},"schema_version":"1.0"},"canonical_sha256":"d57ee9c19152c41826379210c819772c641f3193627b5cc65b13d8d14d3a6c61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:58.719127Z","signature_b64":"7ibAS7aZD5hRFSyrNvveq9R1YN+lIMexnovEanwhqN4nLC/k7K4jnPoH5r1xfGcrmL7M8nm85fGV3HLoaaQyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d57ee9c19152c41826379210c819772c641f3193627b5cc65b13d8d14d3a6c61","last_reissued_at":"2026-05-17T23:38:58.718489Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:58.718489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14764","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wq06dDQ3ZJKhVvsVOQA82+VtyLLTrRTg2Bd5Kmyp3vMmjPKNJKogUva1YB0NzSHIVQrbGPzuSibqvmQD9g8pBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:19:11.104611Z"},"content_sha256":"169d54bd56aa4ae8bec27e4ed44d51829424a44b86fa52e0c1bfac62945bffe9","schema_version":"1.0","event_id":"sha256:169d54bd56aa4ae8bec27e4ed44d51829424a44b86fa52e0c1bfac62945bffe9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2V7OTQMRKLCBQJRXSIIMQGLXFR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compositional Sparsity as an Inductive Bias for Neural Architecture Design","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Antonio Briola, Hongyu Lin, Tomaso Aste, Yuanrong Wang","submitted_at":"2026-05-14T12:26:50Z","abstract_excerpt":"Identifying the structural priors that enable Deep Neural Networks (DNNs) to overcome the curse of dimensionality is a fundamental challenge in machine learning theory. Existing literature suggests that effective high-dimensional learning is driven by compositional sparsity, where target functions decompose into constituents supported on low-dimensional variable subsets. To investigate this hypothesis, we combine Information Filtering Networks (IFNs), which extract sparse dependency structures via constrained information maximisation, with Homological Neural Networks (HNNs), which map the infe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14764","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/SdQmE5uMcPdfasmB6n3Mu1VePgGD9UgiOZtkNRUu9hkVC+3uHoAckWsucS2rQCM5d7Ub8M/Adobv/UaSZQCAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T18:19:11.105263Z"},"content_sha256":"d77ac4de123e9afa80e78571041a852e2d7f93bfea055fd0d5c9cd36e0e8e8f6","schema_version":"1.0","event_id":"sha256:d77ac4de123e9afa80e78571041a852e2d7f93bfea055fd0d5c9cd36e0e8e8f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2V7OTQMRKLCBQJRXSIIMQGLXFR/bundle.json","state_url":"https://pith.science/pith/2V7OTQMRKLCBQJRXSIIMQGLXFR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2V7OTQMRKLCBQJRXSIIMQGLXFR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T18:19:11Z","links":{"resolver":"https://pith.science/pith/2V7OTQMRKLCBQJRXSIIMQGLXFR","bundle":"https://pith.science/pith/2V7OTQMRKLCBQJRXSIIMQGLXFR/bundle.json","state":"https://pith.science/pith/2V7OTQMRKLCBQJRXSIIMQGLXFR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2V7OTQMRKLCBQJRXSIIMQGLXFR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2V7OTQMRKLCBQJRXSIIMQGLXFR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2f0748ca70e2e568eb32c8fee443760b6968f6a69b4f081584bc1f83c399921e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T12:26:50Z","title_canon_sha256":"6369523667ba40a7ed9a90d1ff5526383b2425ac672e3e5cf69697e7595d67c1"},"schema_version":"1.0","source":{"id":"2605.14764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14764","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14764v1","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14764","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"2V7OTQMRKLCB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2V7OTQMRKLCBQJRX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2V7OTQMR","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d77ac4de123e9afa80e78571041a852e2d7f93bfea055fd0d5c9cd36e0e8e8f6","target":"graph","created_at":"2026-05-17T23:38:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Identifying the structural priors that enable Deep Neural Networks (DNNs) to overcome the curse of dimensionality is a fundamental challenge in machine learning theory. Existing literature suggests that effective high-dimensional learning is driven by compositional sparsity, where target functions decompose into constituents supported on low-dimensional variable subsets. To investigate this hypothesis, we combine Information Filtering Networks (IFNs), which extract sparse dependency structures via constrained information maximisation, with Homological Neural Networks (HNNs), which map the infe","authors_text":"Antonio Briola, Hongyu Lin, Tomaso Aste, Yuanrong Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T12:26:50Z","title":"Compositional Sparsity as an Inductive Bias for Neural Architecture Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14764","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:169d54bd56aa4ae8bec27e4ed44d51829424a44b86fa52e0c1bfac62945bffe9","target":"record","created_at":"2026-05-17T23:38:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2f0748ca70e2e568eb32c8fee443760b6968f6a69b4f081584bc1f83c399921e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T12:26:50Z","title_canon_sha256":"6369523667ba40a7ed9a90d1ff5526383b2425ac672e3e5cf69697e7595d67c1"},"schema_version":"1.0","source":{"id":"2605.14764","kind":"arxiv","version":1}},"canonical_sha256":"d57ee9c19152c41826379210c819772c641f3193627b5cc65b13d8d14d3a6c61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d57ee9c19152c41826379210c819772c641f3193627b5cc65b13d8d14d3a6c61","first_computed_at":"2026-05-17T23:38:58.718489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:58.718489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7ibAS7aZD5hRFSyrNvveq9R1YN+lIMexnovEanwhqN4nLC/k7K4jnPoH5r1xfGcrmL7M8nm85fGV3HLoaaQyDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:58.719127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:169d54bd56aa4ae8bec27e4ed44d51829424a44b86fa52e0c1bfac62945bffe9","sha256:d77ac4de123e9afa80e78571041a852e2d7f93bfea055fd0d5c9cd36e0e8e8f6"],"state_sha256":"0278cbabfd8fc2ce8c0a0e029059d7adcb7b4ef2b7b0d66625a34b40db960e6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WjN0T/zKo25CLZWrWWVSbviTsDEnDTjADyF9fmxqtuT5nPMNQQ5NK7gKkYzOHv4ygPkLppMTM8luLfv/XxQDAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T18:19:11.109333Z","bundle_sha256":"f399cfbc7b1fc2a17d3d591c40e383c029fa322375d27f91c60543d53044aade"}}